Our AIBot will use hybrid search, combining both keyword and semantic search. If you didn’t enable embeddings properly, it will only use keyword search. To enable embeddings follow Enable Related Topics. After that it will slowly backfill in the background using the choosen model / provider.
6 לייקים
Any news/updates on how it is working?
We decided to go with Discourse Chatbot because it has some features we need and Robert is helping us build a few additional features to get us all the way there. I’ll post a link when it’s up and running in case you want to try it but it will probably take at least a month.
4 לייקים
Great to hear about that for your forum!
Thanks for the update.
2 לייקים
Maybe RLHF is on the way out.
לייק 1
FYI
Not suggesting this be added but useful for ideas in the future.
“DiagGPT: An LLM-based Chatbot with Automatic Topic Management for Task-Oriented Dialogue” by Lang Cao (pdf )
For those that recognize the info it was also posted here.
2 לייקים
“RAG vs Fine-tuning: pipelines, tradeoffs, and a case study on agriculture” (pdf) by Aman Gupta, Anup Shirgaonkar, Angels Balaguer, Bruno Silva, Daniel Holstein, Dawei Li, Jennifer Marsman, Leonardo Nunes, Mahsa Rouzbahman, Morris Sharp, Nick Mecklenburg, Rafael Padilha, Ranveer Chandra, Renato Cunha, Roberto Estevão, Ryan Tsang, Sara Malvar, Swati Sharma, Todd Hendry, Vijay Aski, Vijetha Vijayendran, Vinamra Benara
It took longer than expected but we finally have our support chatbot live, albeit in “beta testing mode”. Thanks to everyone who offered advice along the way! And special thanks to @merefield for writing the Chatbot plugin! If you’d like to try it, here’s how.
2 לייקים
Had a reason to revisit this post.
Care to share any updates about the bot?
Thanks.
In addition to the guide above, one of the most apparent things is that the bot’s performance depends on how much the user knows. If they ask good questions they’re more likely to get good answers. If they use the wrong terms or describe things poorly in their question, the bot will happily misunderstand and confidently give them an answer anyway. It’s working better for power users than it is for novices. With less knowledgable users, us humans are better at picking up on nuances in their question and understanding what they really mean to ask. Feel free to give it a try, I’d love your feedback.
לייק 1
Saw this recent example AI generated image and thought of your AI bot for technical help.
The image is from an OpenAI cookbook.
https://github.com/openai/openai-cookbook/commit/bba26821fa2bce502503173d27c304278fa223d9
לייק 1
Wow, great image. And FYI Image Gen 2 is now an option on Discourse Chatbot 🤖
2 לייקים
Found the actual OpenAI Cookbook
לייק 1
That’s interesting. Are you thinking there may be a way to use that for technical support?
We experimented with the vision feature in Chatbot interpreting photos of security alarm panels and giving wiring advice. It worked better than I expected. But I don’t think our customers have used that in practice.
לייק 1
Yes.
One idea—among several—is to generate image overlays that include callouts with text, each pointing to a specific component (e.g., a wire, switch, or connector).
Earlier image generation models struggled with rendering technical text accurately. Text was not treated as symbolic content but emerged from diffusion processes, which often produced distorted or unreadable results.
In contrast, the latest model appears to handle text more explicitly. It seems to construct bounded regions (e.g., rectangular containers) and then place text within those regions.
A close inspection of the coffee machine image background reveals multiple layered and interconnected rectangles. These structures are likely artifacts of the image generation pipeline rather than intentional visual elements.
You may also want to review this OpenAI topic, where community members are actively sharing insights and findings.
I used it to make the images in this article.
You’re right. Thats’ a huge improvement from the last time I tried. I remember text melting off the image and weird random symbols showing up before.
2 לייקים
Those images and infographics are awesome!
Care to share the prompts you used along with tips or such in this topic on the OpenAI forum?